Methods and apparatus for HILN determination with a deep adaptation network for both serum and plasma samples
A method of characterizing a serum or plasma portion of a specimen in a specimen container provides an HILN (hemolysis, icterus, lipemia, normal) determination. Pixel data of an input image of the specimen container is processed by a classification network to identify whether the specimen contains plasma or serum. Pixel data representing a plasma sample are forwarded to a segmentation/classification/regression network trained with plasma samples for HILN determination. Pixel data representing a serum sample are forwarded to a transformation network, wherein the serum sample pixel data is transformed into pixel data that matches pixel data of a corresponding previously-collected plasma sample by changing sample color, contrast, intensity, and/or brightness. The transformed serum sample pixel data are forwarded to the segmentation/classification/regression network for HILN determination. Quality check modules and testing apparatus configured to carry out the method are also described, as are other aspects.
1. A method of characterizing a specimen container, comprising:
processing pixel data of an image of a specimen container containing a specimen therein to determine whether the specimen container includes a serum portion or a plasma portion using a classification network executing on a computer; and
transforming pixel data of an image determined by the classification network to include a serum portion into transformed-pixel data that matches pixel data of a previously-collected image of a plasma portion having an appearance that corresponds to an appearance of the serum portion without affecting any HILN (hemolytic, icteric, lipemic, and normal) characteristics present in the pixel data of the image using a transformation network executing on the computer.
2. The method of claim 1 , further comprising:
processing the transformed-pixel data to determine an HILN category of the serum portion using a segmentation/classification/regression network executing on the computer;
processing pixel data of an image determined by the classification network to include a plasma portion to determine an HILN category of the plasma portion using the segmentation/classification/regression network executing on the computer; and
outputting from the segmentation/classification/regression network a determined HILN category for each image having pixel data processed by the segmentation/classification/regression network using an interface module coupled to the computer.
3. The method of claim 2 , wherein the segmentation/classification/regression network has been trained with only images of plasma samples.
4. The method of claim 2 , wherein the outputting further comprises outputting from the segmentation/classification/regression network a classification index category comprising hemolytic, icteric, lipemic, and normal classes and sub-classes using the interface module coupled to the computer.
5. The method of claim 1 , further comprising processing the pixel data of the image of the specimen container to determine whether the specimen container includes an uncentrifuged specimen using the classification network executing on the computer.
6. The method of claim 1 , further comprising removing at least some noise from the pixel data of the image using the transformation network executing on the computer.
7. The method of claim 1 , wherein the transforming comprises modifying pixel color, contrast, intensity, or brightness data of the image determined by the classification network to include the serum portion.
8. A quality check module, comprising:
one or more image capture devices operative to capture one or more images from one or more viewpoints of a specimen container containing a specimen therein; and
a computer coupled to the one or more image capture devices, the computer comprising an interface module and configured and operative to:
process pixel data of a captured image of the specimen container to determine whether the specimen container includes a serum portion or a plasma portion using a classification network executing on the computer;
transform pixel data of a captured image determined by the classification network to include a serum portion into transformed-pixel data that matches pixel data of a previously-collected image of a plasma portion having an appearance that corresponds to an appearance of the serum portion without affecting any HILN (hemolytic, icteric, lipemic, and normal) characteristics present in the pixel data of the image using a transformation network executing on the computer;
process the transformed-pixel data to determine an HILN category of the serum portion using a segmentation/classification/regression network executing on the computer; and
output from the segmentation/classification/regression network using the interface module a determined HILN category for each captured image having pixel data processed by the segmentation/classification/regression network.
9. The quality check module of claim 8 , wherein the segmentation/classification/regression network has been trained with only images of plasma samples.
10. The quality check module of claim 8 , wherein the computer is further configured and operative to process pixel data of a captured image determined by the classification network to include a plasma portion to determine an HILN category of the plasma portion using the segmentation/classification/regression network executing on the computer.
11. The quality check module of claim 8 , wherein the computer is further configured and operative to output from the classification network using the interface module a determination that the specimen is uncentrifuged.
12. The quality check module of claim 8 , wherein the computer is further configured and operative to output from the segmentation/classification/regression network using the interface module a classification index category comprising hemolytic, icteric, lipemic, and normal classes.
13. The quality check module of claim 12 , wherein each of the hemolytic, icteric, and lipemic classes comprises five to seven sub-classes.
14. The quality check module of claim 8 , wherein the computer is further configured and operative to transform the pixel data of the captured image by modifying pixel color, contrast, intensity, or brightness data of the captured image.
15. A specimen testing apparatus, comprising:
a track;
a carrier moveable on the track and configured to contain a specimen container containing a specimen therein;
a plurality of image capture devices arranged around the track and operative to capture one or more images from one or more viewpoints of the specimen container and the specimen; and
a computer coupled to the plurality of image capture devices, the computer comprising an interface module and configured and operative to:
process pixel data of a captured image of the specimen container to determine whether the specimen container includes a serum portion or a plasma portion using a classification network executing on the computer;
transform pixel data of a captured image determined by the classification network to include a serum portion into transformed-pixel data that matches pixel data of a previously-collected image of a plasma portion having an appearance that corresponds to an appearance of the serum portion without affecting any HILN (hemolytic, icteric, lipemic, and normal) characteristics present in the pixel data of the image using a transformation network executing on the computer;
process the transformed-pixel data to determine an HILN category of the serum portion using a segmentation/classification/regression network executing on the computer; and
output from the segmentation/classification/regression network using the interface module a determined HILN category for each captured image having pixel data processed by the segmentation/classification/regression network.
16. The specimen testing apparatus of claim 15 , wherein the segmentation/classification/regression network has been trained with only images of plasma samples.
17. The specimen testing apparatus of claim 15 , wherein the computer is further configured and operative to transform the pixel data of the captured image by modifying pixel color, contrast, intensity, or brightness data of the captured image.
18. The specimen testing apparatus of claim 15 , wherein the computer is further configured and operative to process pixel data of a captured image determined by the classification network to include a plasma portion to determine an HILN category of the plasma portion using the segmentation/classification/regression network executing on the computer.
19. The specimen testing apparatus of claim 15 , wherein the computer is further configured and operative to output from the classification network using the interface module a determination that the specimen is uncentrifuged.
20. The specimen testing apparatus of claim 15 , wherein the computer is further configured and operative to output from the segmentation/classification/regression network using the interface module a classification index category comprising hemolytic, icteric, lipemic, and normal classes and sub-classes.
21. A method of characterizing a specimen container, comprising:
transforming pixel data, using a transformation network executing on a computer, of an image of a specimen container into transformed-pixel data, the specimen container containing a specimen therein, the specimen having a serum portion or a plasma portion, the transformation network minimizing or normalizing appearance differences between images of serum portions and images of plasma portions without affecting any HILN (hemolytic, icteric, lipemic, and normal) characteristics present in the pixel data of the image.